© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11553
    Prev
    Next
    INDEX
    Explanations

    Leopold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lland
    -0.98
     Leopold
    -0.93
    Leopold
    -0.75
    Tikang
    -0.73
     blackout
    -0.71
    gany
    -0.68
    queryInterface
    -0.65
    RoutingModule
    -0.59
     Biôgrafia
    -0.59
     Blackout
    -0.56
    POSITIVE LOGITS
    Hauptartikel
    0.59
     doInBackground
    0.54
    ChildScrollView
    0.49
    /**
    0.49
    mazioni
    0.47
    setDo
    0.46
    AddTagHelper
    0.44
     ')[
    0.44
     <=",
    0.43
    TopLeft
    0.43
    Activations Density 0.154%

    No Known Activations